// SCAN REPORT

MidOS - MCP Community Library

25 tools. 4 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 28 Jun 2026

4 can modify or destroy data

21 read-only

25 tools total

Community server · catalogue entry verified 28/06/2026

How to control MidOS - MCP Community Library ↓

TOOL MAP

What MidOS - MCP Community Library exposes to your agents

Read (21) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous MidOS - MCP Community Library tools

Execute · High pool_signal Signaling an action to a multi-instance coordination pool triggers external operations or state changes across potentially many running agent instances. Write · Medium midos_submit Submission to an inbox is reversible—the task can typically be removed, paused, or modified before processing. Write · Medium episodic_store The tool creates/writes new data (episodic memories or reflections) to a persistent store.

4 of MidOS - MCP Community Library's 25 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MidOS - MCP Community Library

PolicyLayer is an MCP gateway — it sits between your AI agents and MidOS - MCP Community Library, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "episodic_store": {
    "limits": [
      {
        "counter": "episodic_store_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "agent_bootstrap": {
    "limits": [
      {
        "counter": "agent_bootstrap_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MidOS - MCP Community Library — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MIDOS - MCP COMMUNITY LIBRARY →

Instant setup, no code required.

FULL CATALOGUE

All 25 MidOS - MCP Community Library tools

EXECUTE 1 tools

Execute pool_signal Signal an action to the multi-instance coordination pool.

WRITE 2 tools

Write episodic_store Store a new episodic memory/reflection for future learning. Write midos_submit Submit a task to MidOS inbox for async processing.

READ 21 tools

Read agent_bootstrap [DEPRECATED -- use agent_handshake instead] Generic agent onboarding. Returns default config for unknown agent Read chunk_code Parse code file into semantic chunks (functions, classes, methods) for better RAG retrieval. Read episodic_search Search episodic memory for similar past experiences using vector similarity. Read get_eureka Get a specific EUREKA breakthrough document. Read get_protocol Get a specific protocol document. Read get_skill Get a specific skill/capability document by name. Read get_truth Get a specific truth patch document. Read hive_status Get current status of the Midos hive system. Read list_skills List all available skills/capabilities. Read memory_stats Get statistics about the Midos memory system (LanceDB chunks, cache status). Read midos_ask Ask MidOS knowledge base a question. Returns matches from knowledge + EUREKA. Read midos_bootstrap Agent onboarding. Returns identity, architecture, available tools, skills, guardrails, and quick-start command Read midos_eureka Search only EUREKA validated knowledge (high-quality findings). Read midos_search Search MidOS knowledge base for a topic. Returns ranked results. Read midos_skills List all available MidOS skills. Read midos_topology Get the MidOS system architecture map. Read pool_status Get multi-instance coordination pool status and recent activity. Read project_status project_status Read research_youtube Queue a YouTube video for research. Midos will transcribe and extract insights. Read search_knowledge Search the Midos knowledge base for relevant information. Read semantic_search semantic_search

OTHER 1 tools

Other agent_handshake agent_handshake

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about MidOS - MCP Community Library

How do I prevent bulk modifications through MidOS - MCP Community Library? +

The MidOS - MCP Community Library server has 2 write tools including episodic_store, midos_submit. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MidOS - MCP Community Library.

How many tools does the MidOS - MCP Community Library MCP server expose? +

25 tools across 3 categories: Execute, Read, Write. 21 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on MidOS - MCP Community Library? +

Register the MidOS - MCP Community Library MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MidOS - MCP Community Library tool call.

Deterministic rules across all 25 MidOS - MCP Community Library tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MIDOS - MCP COMMUNITY LIBRARY →

Instant setup, no code required.

25 MidOS - MCP Community Library tools catalogued and risk-classified — across an index of 43,000+ MCP servers.